神经网络向量化

@@ Line 161: / Line 161: @@
 ==中英文对照==
-:反向传播算法	Backpropagation Algorithm
+:向量化	        vectorization
-:（批量）梯度下降法	(batch) gradient descent
+:正向传导	forward Propagation
-:（整体）代价函数	(overall) cost function
+:反向传导	backpropagation
-:方差	squared-error
+:训练样本	training examples
-:均方差	average sum-of-squares error
-:规则化项	regularization term
-:权重衰减	weight decay
-:偏置项	bias terms
-:贝叶斯规则化方法	Bayesian regularization method
-:高斯先验概率	Gaussian prior
-:极大后验估计	MAP
-:极大似然估计	maximum likelihood estimation
 :激活函数	activation function
-:双曲正切函数	tanh function
+:自编码网络	autoencoder
-:非凸函数	non-convex function
+:稀疏惩罚	sparsity penalty
-:隐藏层单元	hidden (layer) units
-:对称失效	 symmetry breaking
-:学习速率	learning rate
-:前向传导	forward pass
-:假设值	hypothesis
-:残差	error term
-:加权平均值	weighted average
-:前馈传导	feedforward pass
-:阿达马乘积	Hadamard product
-:前向传播	forward propagation
 ==中文译者==

Revision as of 14:04, 6 April 2013